- Railway Systems and Energy Efficiency
- Power Systems and Technologies
- Video Surveillance and Tracking Methods
- Advanced Fiber Optic Sensors
- Railway Engineering and Dynamics
- Indoor and Outdoor Localization Technologies
- Technology and Security Systems
- Software Reliability and Analysis Research
- Infrared Target Detection Methodologies
- Advanced Software Engineering Methodologies
- Traffic Prediction and Management Techniques
- Software Testing and Debugging Techniques
- Power Line Communications and Noise
- Image Processing and 3D Reconstruction
- Power System Reliability and Maintenance
- Industrial Technology and Control Systems
- Software System Performance and Reliability
- Millimeter-Wave Propagation and Modeling
- Chaos-based Image/Signal Encryption
- Air Quality and Health Impacts
- Formal Methods in Verification
- Agricultural and Environmental Management
- Blockchain Technology Applications and Security
- Advanced Computing and Algorithms
- Photonic Crystal and Fiber Optics
China Academy of Railway Sciences
2020-2025
Beijing University of Posts and Telecommunications
2024
Rooftop solar photovoltaic (PV) retrofitting can greatly reduce the emissions of greenhouse gases, thus contributing to carbon neutrality. Effective assessment emission reduction has become an urgent challenge for government and business enterprises. In this study, we propose a method assess accurately potential long-term by installing PV on rooftops. This is achieved using joint action GF-2 satellite images, Point Interest (POI) data, meteorological data. Firstly, introduce building...
Evacuation simulations in virtual indoor fire scenes hold great significance for public safety. However, existing evacuation simulation methods are inefficient and provide poor visualized when applied to reality (VR) simulations. Additionally, the influences of interaction processes on choice multiple exits have not been fully considered. In paper, we propose a VR method crowd multiexit environment. An 3D scene model character model, studying environmental factors that affect selection...
Abstract To capture local complex shape information and fine-grained features from irregular point cloud, this paper proposes a novel feature encoder-based network named CA-Net which is used to solve the challenge of 3D object classification segmentation. The core CA-Encoder, based on context-awareness (CA) cross-channel multi-head self-attention (CC-MSA). CA-Encoder uses contextual awareness aggregate two levels: cloud coordinate high-dimensional implicitly encoded information, leveraging...
We present an anti-noise ϕ-optical time-domain reflectometer-based distributed acoustic sensing system that can effectively differentiate noise and interference for high-speed railway intrusion detection. A interrogator unit, based on digital heterodyne detection, was deployed in a real field station three types of signals were collected, including wall climbing, breaking, barbed wire crossing. Sensing analyzed identified by comprehensive deep model which consisted temporal relation...
Virtual coupling is a novel railway transport concept that allows trains to split and join on-the-fly by switching from mechanical virtual couplers. One of the main challenges in applying metro railways reduce tracking distance between without compromising safety. This paper proposes relative operation-based train separation model safe trains. applies fault tolerance principle. The principle preceding normally operates for time interval its last-known state before initiating an emergency...
Correlation filter (CF) is widely used in unmanned aerial vehicle (UAV) tracking because of its efficient performance. However, due to the existence edge effects, CF will be confused so that peak response no longer obvious, resulting drift and template degradation, thereby degrading To handle problem, we propose a new for this problem. First, introduce response-weighted background residual term make learn targeted manner according strength response. Secondly, history model constructed...
Research on virtual coupling has made further progress. It needs many tests before operation. The problem of connecting the new railway with existing will arise. increasingly large and complex hubs make a test difficult. Test system, especially combined test, heavy workload. Restricted by time influence transportation, it is challenging to discover defects hidden dangers systems through dynamic on-site procedures. laboratory "full scene, full elements" engineering testing urgently be...
Accurate and fine-grained individual air quality index (IAQI) prediction is the basis of (AQI), which great significance for control human health. Traditional approaches, such as time series, recurrent neural network or graph convolutional network, cannot effectively integrate spatial-temporal meteorological factors manage dynamic edge relationship among scattered monitoring stations. In this paper, a ST-CCN-IAQI model proposed based on causal convolution networks. Both spatial effects...
Vehicular reputation maintenance with distributed ledger is aimed at establishing trust among vehicles randomly meeting in a Ad-hoc Network (VANET). It is, however, challenging VANET, as congested areas road networks, brought by traffic tides or accidents, challenge the performance. Meanwhile, update highly dependent on transaction consensus of ledger. To solve problem, this paper proposes deploying directed acyclic graph- (DAG-) based ledgers vehicles, which use vehicular distribution to...
Testing is an important safety assurance technique for railway interlocking systems. Model-based testing (MBT) allows designing and maintaining tests with high-level models generating test suites from these automatically. Although MBT has the potential to improve efficiency quality, it not clear whether this applicable complex variant-rich software. In paper, we report our experience in introducing inter-locking testing. We develop feature of route control process reusability models. The...
In recent years, virtual coupling has been proposed as a novel railway transportation method to achieve zero capacity waste with full reliability, flexibility and accessibility. To maintain platoons stable in coupling, the speed of preceding train must be predicted precisely by combing planned control outputs dynamic models. Unfortunately, hindered complicated wheel-rail interaction mechanisms, accurate is difficult modeled conventional methods. This paper proposes long short term memory...
The ZPW-2000K jointless track circuit is composed of the main and small in tuning area. Aiming at complexity randomness area failure, an intelligent diagnosis model support vector machine(SVM) based on particle swarm optimization(PSO) proposed. Firstly, according to structural composition area, 10 voltage current monitoring quantities system passenger dedicated line are selected form fault data feature set. Secondly, optimization used MATLAB optimize SVM parameters, with optimal parameters...
In this paper, a relay-based ACK selective cooperative diversity transmission mode is proposed for high-speed railway. The primary intention of paper to evaluate the performance non-relay direct and with acknowledgment mode. What's more, closed-form outage probabilities each are derived. We can conclude that has better as well reliability than by comparing their probability especially in railway scenario. It also be noted attenuation signal amplitude caused carriage passing loss crucial...
Abstract Due to its quick computation, the correlation filter (CF) is frequently employed in object-tracking activities. The occlusion and deformation of tracking object during CF process will pollute filter, which cause filter’s performance degrade. This especially obvious unmanned aerial vehicle (UAV) increased interfered sequences further aggravate problem. In response this problem, we use ARCF as baseline add a spatial-temporal regularization term based on adaptive template. We also...
High-Speed Railway (HSR) measurement is very difficult, with the limitation of policy, complexity, cost and safety constraints. A technique performing high velocity at low has been proposed in existing literature, which not studied well environment. In this paper, experimental assessment from perspective wireless channel parameters presented. Specifically, two controlled measurements center frequency 465 MHz are conducted, then characteristics such as path loss, shadowing fading, Doppler...
Abstract Train-centric communication based train control (TcCBTC) system contains a variety of uncertain factors in the operation process, and generation scenario movement authority is real-time process. In order to judge impact on safety, it necessary conduct formal modeling analysis for this implementation Aiming at an environment, firstly, process TcCBTC was analyzed, hazard source identification carried out by combining operability study (HAZOP) method. Secondly, modeled stochastic...
In view of the contradiction between large demand for rail transit signal and control talents lack professional teachers as well urgent need to improve training quality talents, construction virtual teaching research center is carried out through interschool school-enterprise joint ventures, so meet needs talent training. Taking specialty Lanzhou Jiaotong University an example, this paper discusses connotation, content, characteristics provide reference center.